Journal of Biomolecular Structure & Dynamics最新文献

{"title":"Discovery of novel IDO1/TDO2 dual inhibitors: a consensus Virtual screening approach with molecular dynamics simulations, and binding free energy analysis.","authors":"Naufa Hanif, Suat Sari","doi":"10.1080/07391102.2024.2329302","DOIUrl":"10.1080/07391102.2024.2329302","url":null,"abstract":"<p><p>The pursuit of effective cancer immunotherapy drugs remains challenging, with overexpression of indoleamine 2,3-dioxygenase 1 (IDO1) and tryptophan 2,3-dioxygenase 2 (TDO2) allowing cancer cells to evade immune attacks. While several IDO1 inhibitors have undergone clinical testing, only three dual IDO1/TDO2 inhibitors have reached human trials. Hence, this study focuses on identifying novel IDO1/TDO2 dual inhibitors through consensus structure-based virtual screening (SBVS). ZINC15 natural products library was refined based on molecular descriptors, and the selected compounds were docked to the holo form IDO1 and TDO2 using two different software programs and ranked according to their consensus docking scores. The top-scoring compounds underwent in silico evaluations for pharmacokinetics, toxicity, CYP3A4 affinity, molecular dynamics (MD) simulations, and MM-GBSA binding free energy calculations. Five compounds (ZINC00000079405/<b>10,</b> ZINC00004028612/<b>11</b>, ZINC00013380497/<b>12</b>, ZINC00014613023/<b>13,</b> and ZINC00103579819/<b>14</b>) were identified as potential IDO1/TDO2 dual inhibitors due to their high consensus docking scores, key residue interactions with the enzymes, favorable pharmacokinetics, and avoidance of CYP3A4 binding. MD simulations of the top three hits with IDO1 indicated conformational changes and compactness, while MM-GBSA analysis revealed strong binding free energy for compounds <b>10</b> (ΔG: -20.13 kcal/mol) and <b>11</b> (ΔG: -16.22 kcal/mol). These virtual hits signify a promising initial step in identifying candidates as supplementary therapeutics to immune checkpoint inhibitors in cancer treatment. Their potential to deliver potent dual inhibition of IDO1/TDO2, along with safety and favorable pharmacokinetics, makes them compelling. Validation through <i>in vitro</i> and <i>in vivo</i> assays should be conducted to confirm their activity, selectivity, and preclinical potential as holo IDO1/TDO2 dual inhibitors.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"6954-6970"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140158233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TOLEDO: enhancing Maestro GUI for non-expert users to perform massive MD simulations.","authors":"Miguel Carmena-Bargueño, Carlos Martínez-Cortés, Antonio Jesús Banegas-Luna, Horacio Pérez-Sánchez","doi":"10.1080/07391102.2024.2423380","DOIUrl":"10.1080/07391102.2024.2423380","url":null,"abstract":"<p><p>Classical Molecular Dynamics (MD) simulates the dynamical evolution of biological systems at the atomic level. Using MD in conjunction with high-performance computing (HPC) architectures, we can evaluate the possible interactions between a ligand library against one protein target to find a drug that can influence a protein target to cure a disease. Simultaneously, we can also obtain information about their dynamic evolution. One of the primary software packages for MD simulations is Desmond, which employs Maestro for the setup, execution, and analysis of MD through a graphical user interface (GUI), which is suitable even for non-expert users. However, using the GUI, users can typically run only one short (less than 1000 ns) MD each time. Our work aims to create a method/protocol to run several MD simulations simultaneously on a remote HPC cluster within Maestro-Desmond. In this work, we provide TOLEDO (Throughput Optimization of Ligand-Protein Systems Exploration through Dynamics simulation in Optimized HPC systems) to overcome such limitations and run several MD simulations simultaneously. The best feature of TOLEDO is its independence from the usual time constraints of many clusters, with storage space being the only limitation. To run TOLEDO, we prepare/set up the protein-ligand complex before running MD <i>via</i> Maestro GUI. Next, we run the main TOLEDO script for several MD simulations on a supercomputer. When TOLEDO finishes, users obtain reports and graphics. The obtained results are easily interpretable. In essence, TOLEDO significantly enhances MD throughput beyond the capabilities of the Maestro GUI.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"7096-7105"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142576092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment of iridoids and their similar structures as antineoplastic drugs by <i>in silico</i> approach.","authors":"Prabhat Neupane, Jhashanath Adhikari Subin, Rameshwar Adhikari","doi":"10.1080/07391102.2024.2314262","DOIUrl":"10.1080/07391102.2024.2314262","url":null,"abstract":"<p><p>Iridoids commonly found in plants as secondary metabolites have been reported to possess significant biological activities such as anticancer, antioxidant, hypoglycemic, antimicrobial etc. The strong interactions of iridoids with cyclic-dependent kinase 8 (CDK8) protein could show inhibitory effects that could modulate tumour growth. From the molecular docking calculations, some iridoids interacted effectively with the target CDK8 protein (PDB ID: 5ICP) with better binding affinities of -9.1, -9.0, -9.0, -8.9 kcal/mol, than that observed for the native ligand with -8.7 kcal/mol and for the reference compound gemcitabine with -6.9 kcal/mol. The GI₅₀ values (<5 μM) obtained from graph-based signatures showed activity in breast, colon, leukaemia, and renal cancer cell lines. The IC₅₀ predictions as CDK2 inhibitors were greater than 10 µM with type I non-allosteric binding mode. The stability analysis of protein-ligand complex from 125 ns long molecular dynamics simulations showed moderately smooth trajectories and RSMD value around 5 Å for the docked ligands. The binding free energy changes up to -47.65 ± 5.97 kcal/mol from MMGBSA method and -30.33 ± 5.40 kcal/mol from MMPBSA method hinted at the spontaneous nature of the complex formation. Furthermore, geometrical evaluators like RMSF, R_g, SASA, and hydrogen bond count also corroborated with the structural stability of the complexes and the capacity of hit molecules to inhibit the target, indicating its therapeutic potential against cancer. The toxicity and drug-likeness from ADMET predictions suggested experimental verification and that the proposed candidates could be employed for further trials in the development of safer and more effective anticancer drugs.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"5966-5981"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139722759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning and molecular simulation-based protocols to identify novel potential inhibitors for reverse transcriptase against HIV infections.","authors":"Muhammad Shahab, Guojun Zheng, Yousef A Bin Jardan, Mohammed Bourhia","doi":"10.1080/07391102.2024.2319112","DOIUrl":"10.1080/07391102.2024.2319112","url":null,"abstract":"<p><p>Acquired immunodeficiency syndrome (AIDS) is a potentially fatal condition affecting the human immune system, which is attributed to the human immunodeficiency virus (HIV). The suppression of reverse transcriptase activity is a promising and feasible strategy for the therapeutic management of AIDS. In this study, we employed machine learning algorithms, such as support vector machines (SVM), k-nearest neighbor (k-NN), random forest (RF), and Gaussian naive base (GNB), which are fast and effective tools commonly used in drug design. For model training, we initially obtained a dataset of 5,159 compounds from BindingDB. The models were assessed using tenfold cross-validation to ensure their accuracy and reliability. Among these compounds, 1,645 compounds were labeled as active, having an IC₅₀ below 0.49 µM, while 3,514 compounds were labeled \"inactive against reverse transcriptase. Random forest achieved 86% accuracy on the train and test set among the different machine learning algorithms. Random forest model was then applied to an external ZINC dataset. Subsequently, only three hits-ZINC1359750464, ZINC1435357562, and ZINC1545719422-were selected based on the Lipinski Rule, docking score, and good interaction. The stability of these molecules was further evaluated by deploying molecular dynamics simulation and MM/GBSA, which were found to be -38.6013 ± 0.1103 kcal/mol for the Zidovudine/RT complex, -59.1761 ± 2.2926 kcal/mol for the ZINC1359750464/RT complex, -47.6292 ± 2.4206 kcal/mol for the ZINC1435357562/RT complex, and -50.7334 ± 2.5713 kcal/mol for the ZINC1545719422/RT complex.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"6109-6122"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139912699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PEDF inhibits VEGF-induced vascular leakage through binding to VEGFR2 in acute myocardial infarction.","authors":"Hong-Liang Hui, Bo Jiang, Yan-Ying Zhou, Fan Qiu, Yan-Gui Lin, Hua-Ming Li, Dan Li, Min Luo, Hao-Ran Miao, Sang-Bing Ong, Yi-Qian Zhang","doi":"10.1080/07391102.2024.2314260","DOIUrl":"10.1080/07391102.2024.2314260","url":null,"abstract":"<p><p>Pigment epithelium-derived factor (PEDF) could bind to vascular endothelial growth factor receptor 2 (VEGFR2) and inhibit its activation induced by VEGF. But how PEDF affects VEGFR2 pathway is still poorly understood. In this study, we elucidated the precise mechanism underlying the interaction between PEDF and VEGFR2, and subsequently corroborated our findings using a rat AMI model. PEDF prevented endocytosis of VE-cadherin induced by hypoxia, thereby protecting the endothelium integrity. A three-dimensional model of the VEGFR2-PEDF complex was constructed by protein-protein docking method. The results showed that the VEGFR2-PEDF complex was stable during the simulation. Hydrogen bonds, binding energy and binding modes were analyzed during molecular dynamics simulations, which indicated that hydrogen bonds and hydrophobic interactions were important for the recognition of VEGFR2 with PEDF. In addition, the results from exudation of fibrinogen suggested that PEDF inhibits vascular leakage in acute myocardial infarction and confirmed the critical role of key amino acids in the regulation of endothelial cell permeability. This observation is also supported by echocardiography studies showing that the 34mer peptide sustained cardiac function during acute myocardial infarction. Besides, PEDF and 34mer could inhibit the aggregation of myofiber in the heart and promoted the formation of a dense cell layer in cardiomyocytes, which suggested that PEDF and 34mer peptide protect against AMI-induced cardiac dysfunction. These results suggest that PEDF inhibits the phosphorylation of downstream proteins, thereby preventing vascular leakage, which provides a new therapeutic direction for the treatment of acute myocardial infarction.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"5953-5965"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139722732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the Antarctic aminopeptidase P from <i>Pseudomonas</i> sp. strain AMS3 through structural analysis and molecular dynamics simulation.","authors":"Muhamad Nadzmi Omar, Raja Noor Zaliha Raja Abd Rahman, Noor Dina Muhd Noor, Wahhida Latip, Victor Feizal Knight, Mohd Shukuri Mohamad Ali","doi":"10.1080/07391102.2024.2331093","DOIUrl":"10.1080/07391102.2024.2331093","url":null,"abstract":"<p><p>Aminopeptidase P (APPro) is a crucial metalloaminopeptidase involved in amino acid cleavage from peptide N-termini, playing essential roles as versatile biocatalysts with applications ranging from pharmaceuticals to industrial processes. Despite acknowledging its potential for catalysis in lower temperatures, detailed molecular basis and biotechnological implications in cold environments are yet to be explored. Therefore, this research aims to investigate the molecular mechanisms underlying the cold-adapted characteristics of APPro from <i>Pseudomonas</i> sp. strain AMS3 (AMS3-APPro) through a detailed analysis of its structure and dynamics. In this study, structure analysis and molecular dynamics (MD) simulation of a predicted model of AMS3-APPro has been performed at different temperatures to assess structural flexibility and thermostability across a temperature range of 0-60 °C over 100 ns. The MD simulation results revealed that the structure were able to remain stable at low temperatures. Increased temperatures present a potential threat to the overall stability of AMS3-APPro by disrupting the intricate hydrogen bond networks crucial for maintaining structural integrity, thereby increasing the likelihood of protein unfolding. While the metal binding site at the catalytic core exhibits resilience at higher temperatures, highlighting its local structural integrity, the overall enzyme structure undergoes fluctuations and potential denaturation. This extensive structural instability surpasses the localized stability observed at the metal binding site. Consequently, these assessments offer in-depth understanding of the cold-adapted characteristics of AMS3-APPro, highlighting its capability to uphold its native conformation and stability in low-temperature environments. In summary, this research provides valuable insights into the cold-adapted features of AMS3-APPro, suggesting its efficient operation in low thermal conditions, particularly relevant for potential biotechnological applications in cold environments.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"6239-6251"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140331736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revisiting <i>Plasmodium falciparum</i> P-type ATPase 4 in malarial: ADMET, mutation effect, and molecular simulation studies of potential inhibitors.","authors":"Iseoluwa Isaac Ajayi, Toluwase Hezekiah Fatoki, Ayodele Sunday Alonge, Courage Dele Famusiwa, Ibrahim Olabayode Saliu, Blessing Anuoluwapo Ejimadu, Mayowa Oluwalana Obafemi","doi":"10.1080/07391102.2025.2516757","DOIUrl":"10.1080/07391102.2025.2516757","url":null,"abstract":"<p><p>Malaria, a life-threatening disease caused by Plasmodium parasites, remains a major global health concern, with 247 million cases and approximately 627,000 deaths reported in 2020 across 84 malaria-endemic countries. The <i>Plasmodium falciparum</i> P-type ATPase 4 (PfATP4) gene is expressed throughout the parasite's asexual erythrocytic cycle and plays a vital role in regulating sodium ion levels in the plasma membrane. This study aimed to computationally evaluate selected clinical candidate compounds targeting PfATP4, focusing on their pharmacokinetics and molecular binding characteristics to support further drug development. Pharmacokinetic analyses revealed that Concanamycin A, Maduramicin, and GNF-Pf4492 exhibit low gastrointestinal absorption, while Brefeldin A, MMV396719, MMV006239, and Cipargamin can cross the blood-brain barrier. Among these, Brefeldin A and MMV006239 showed the lowest toxicity. Molecular docking revealed that (+)-SJ733 had the highest binding affinity (-8.891 kcal/mol), followed by MMV665878 (-7.796 kcal/mol) and Maduramicin (-7.791 kcal/mol). All 11 compounds showed binding affinities below -7.000 kcal/mol. Molecular dynamics simulations indicated stable interactions between PfATP4 and both (+)-SJ733 and MMV665878, involving key residues such as PHE917, GLN921, ARG985, and THR993. MMGBSA analysis showed that the MMV665878-PfATP4 complex was more stable and energetically favorable than the (+)-SJ733-PfATP4 complex under simulated physiological conditions. In conclusion, (+)-SJ733 and MMV665878 demonstrate strong potential as PfATP4 inhibitors, with different interaction profiles. Further <i>in vivo</i> and pharmacometric studies are required to validate their efficacy and determine optimal dosing strategies for malaria treatment.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"6419-6434"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144289451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Attenuation of Type IV pili activity by natural products.","authors":"Kerem Yalkut, Soumaya Ben Ali Hassine, Esra Basaran, Ceyda Kula, Aslıhan Ozcan, Fatma Gizem Avci, Ozlem Keskin, Berna Sariyar Akbulut, Pemra Ozbek","doi":"10.1080/07391102.2024.2310781","DOIUrl":"10.1080/07391102.2024.2310781","url":null,"abstract":"<p><p>The virulence factor Type IV pili (T4P) are surface appendages used by the opportunistic pathogen <i>Pseudomonas aeruginosa</i> for twitching motility and adhesion in the environment and during infection. Additionally, the use of these appendages by <i>P. aeruginosa</i> for biofilm formation increases its virulence and drug resistance. Therefore, attenuation of the activity of T4P would be desirable to control <i>P. aeruginosa</i> infections. Here, a computational approach has been pursued to screen natural products that can be used for this purpose. PilB, the elongation ATPase of the T4P machinery in <i>P. aeruginosa</i>, has been selected as the target subunit and virtual screening of FDA-approved drugs has been conducted. Screening identified two natural compounds, ergoloid and irinotecan, as potential candidates for inhibiting this T4P-associated ATPase in <i>P. aeruginosa</i>. These candidate compounds underwent further rigorous evaluation through molecular dynamics (MD) simulations and then through <i>in vitro</i> twitching motility and biofilm inhibition assays. Notably, ergoloid emerged as a particularly promising candidate for weakening the T4P activity by inhibiting the elongation ATPases associated with T4P. This repurposing study paves the way for the timely discovery of antivirulence drugs as an alternative to classical antibiotic treatments to help combat infections caused by <i>P. aeruginosa</i> and related pathogens.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"5719-5729"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139671898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent deep learning-based disease monitoring system in 5G network using multi-disease big data.","authors":"Anupam Das","doi":"10.1080/07391102.2024.2310785","DOIUrl":"10.1080/07391102.2024.2310785","url":null,"abstract":"<p><p>Recently, real-world disease monitoring techniques designed based on wearable medical equipment efficiently minimize the mortality rate. Initially, the data are manually collected from the patients to predict five diseases using 5 G frameworks. Then, the collected data are pre-processed to obtain high-quality data using the techniques like contrast enhancement, median filtering, fill empty space, remove repeated value and stemming. The pre-processed data are taken for extracting the features using a One-Dimensional Convolutional Neural Network (1D-CNN) to obtain the deep features. The parameters like hidden neuron count and epoch are tuned by the proposed Modified Predator Presence Probability-based Squirrel Search-Glowworm Swarm Optimization (MPPP-SSGSO) algorithm to enhance the variance. Then, the extracted features acquired using the 1D-CNN are given to the ensemble boosting-based models for predicting the score, which is combined by comprising approaches like Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost) and Category Boosting (CatBoost). Further, the predicted scores obtained from such models are concatenated and passed to the Ensemble Boosting Scores-based Fuzzy Classifier (EBS-FC) for classifying the five different diseases. Here, the membership function of the fuzzy is optimized by the same developed MPPP-SSGSO algorithm for enhancing accuracy. Experiments are conducted, and validation is performed, which showcased that the recommended framework achieved a better outcome rate than the conventional techniques. Finally, the suggested strategy outperforms the current state-of-the-art methods with an accuracy rate of 91.34%.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"5730-5755"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139706895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel stacking-based predictor for accurate prediction of antimicrobial peptides.","authors":"Sameera Kanwal, Roha Arif, Saeed Ahmed, Muhammad Kabir","doi":"10.1080/07391102.2024.2329298","DOIUrl":"10.1080/07391102.2024.2329298","url":null,"abstract":"<p><p>Antimicrobial peptides (AMPs) are gaining acceptance and support as a chief antibiotic substitute since they boost human immunity. They retain a wide range of actions and have a low risk of developing resistance, which are critical properties to the pharmaceutical industry for drug discovery. Antibiotic sensitivity, however, is an issue that affects people all around the world and has the potential to one day lead to an epidemic. As cutting-edge therapeutic agents, AMPs are also expected to cure microbial infections. In order to produce tolerable drugs, it is crucial to understand the significance of the basic architecture of AMPs. Traditional laboratory methods are expensive and time-consuming for AMPs testing and detection. Currently, bioinformatics techniques are being successfully applied to the detection of AMPs. In this study, we have developed a novel <b>ST</b>acking-based ensemble learning framework for <b>A</b>nti<b>M</b>icrobial <b>P</b>eptide (STAMP) prediction. First, we constructed 84 different baseline models by using 12 different feature encoding schemes and 7 popular machine learning algorithms. Second, these baseline models were trained and employed to create a new probabilistic feature vector. Finally, based on the feature selection strategy, we determined the optimal probabilistic feature vector, which was further utilized for the construction of our stacked model. Resultantly, the STAMP predictor achieved excellent performance during cross-validation with an accuracy and Matthew's correlation coefficient of 0.930 and 0.860, respectively. The corresponding metrics during the independent test were 0.710 and 0.464, respectively. Overall, STAMP achieved a more accurate and stable performance than the baseline models and significantly outperformed the existing predictors, demonstrating the effectiveness of our proposed hybrid framework. Furthermore, STAMP is expected to assist community-wide efforts in identifying AMPs and will contribute to the development of novel therapeutic methods and drug-design for immunity.</p>","PeriodicalId":15272,"journal":{"name":"Journal of Biomolecular Structure & Dynamics","volume":" ","pages":"6202-6213"},"PeriodicalIF":2.4,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140158229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}